R help - Jun 2007 - test for nested factors

Is there a conventional way to test for nested factors?  I.e., if 'a' 
and 'b' are lists of same-length factors, does each level specified by 
'a' correspond to exactly one level specified by 'b'?

The function below seems to suffice, but I'd be happy to know of a more 
succinct solution, if it already exists.

Thanks,

Tim.

---

"%nested.in%" <- function(x,f,...){
	#coerce to list
	if(!is.list(x))x<-list(x)
	if(!is.list(f))f<-list(f)
	#collapse to vector
	x <- tapply(x[[1]],x)
	f <- tapply(f[[1]],f)
	#analyse
	return(all(sapply(lapply(split(f,x),unique),length)==1))
}

CO2$Plant %nested.in% CO2[,c("Type","Treatment")] #TRUE
CO2$Plant %nested.in% (CO2$uptake < mean(CO2$uptake)) #FALSE

On 6/4/07, Tim Bergsma <timb at metrumrg.com>
wrote:
> Is there a conventional way to test for nested factors?  I.e., if
'a'
> and 'b' are lists of same-length factors, does each level specified
by
> 'a' correspond to exactly one level specified by 'b'?
>
> The function below seems to suffice, but I'd be happy to know of a more
> succinct solution, if it already exists.
How about:

"%nested%" <- function(a, b) {
	if (is.list(a)) a <- do.call("interaction", c(a, drop=TRUE))
	if (is.list(b)) b <- do.call("interaction", c(b, drop=TRUE))
	
	length(unique(a))  == length(unique(interaction(a, b, drop=TRUE)))
}

CO2$Plant %nested% CO2[,c("Type","Treatment")] #TRUE
CO2$Plant %nested% (CO2$uptake < mean(CO2$uptake)) #FALSE

?

Hadley

Here are two functions I wrote, 'is.nested' and 'are.crossed',
that check
whether a factor is nested inside antoher one, or if both are crossed:

is.nested <- function (factor1,factor2)
  {
    # only one positive number per line in the f1 * f2 crosstable
    all(apply(table(factor1,factor2)>0,1,sum) == 1)
  }

are.crossed <- function (factor1,factor2)
  { all(table(factor1,factor2) > 0 ) }

Christophe Pallier
www.pallier.org

On 6/4/07, Tim Bergsma <timb@metrumrg.com> wrote:
>
> Is there a conventional way to test for nested factors?  I.e., if
'a'
> and 'b' are lists of same-length factors, does each level specified
by
> 'a' correspond to exactly one level specified by 'b'?
>
> The function below seems to suffice, but I'd be happy to know of a more
> succinct solution, if it already exists.
>
> Thanks,
>
> Tim.
>
> ---
>
> "%nested.in%" <- function(x,f,...){
>         #coerce to list
>         if(!is.list(x))x<-list(x)
>         if(!is.list(f))f<-list(f)
>         #collapse to vector
>         x <- tapply(x[[1]],x)
>         f <- tapply(f[[1]],f)
>         #analyse
>         return(all(sapply(lapply(split(f,x),unique),length)==1))
> }
>
> CO2$Plant %nested.in% CO2[,c("Type","Treatment")] #TRUE
> CO2$Plant %nested.in% (CO2$uptake < mean(CO2$uptake)) #FALSE
>
> ______________________________________________
> R-help@stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>


-- 
Christophe Pallier (http://www.pallier.org)

	[[alternative HTML version deleted]]

Tim Bergsma wrote:
> Is there a conventional way to test for nested factors?  I.e., if
'a'
> and 'b' are lists of same-length factors, does each level specified
by
> 'a' correspond to exactly one level specified by 'b'?
all( tapply(b, a, function(x) length(unique(x))==1 ))


J. R. M. Hosking